© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9981
    Prev
    Next
    INDEX
    Explanations

    C++ code where boost libraries are used, and standard text where the word document appears

    oai_token-act-pair · gemini-2.0-flash

    ini

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الإنجليزية
    -0.65
     mesmo
    -0.50
     ***!
    -0.50
    UserScript
    -0.48
     bety
    -0.45
    φό
    -0.43
    拱
    -0.43
    
    -0.42
    Marne
    -0.42
    Personensuche
    -0.42
    POSITIVE LOGITS
     itſelf
    0.72
     تضيفلها
    0.69
     Efq
    0.68
     ſeveral
    0.66
     ProtoMessage
    0.65
     myſelf
    0.65
     ſmall
    0.63
     }}"></
    0.63
     ſtate
    0.62
     neceff
    0.60
    Activations Density 1.650%

    No Known Activations